刚入手还没捂热的爬虫,如有不足的地方望大佬指点一番
import urllib.request
import json
import re
url = 'https://dianying.taobao.com/showAction.json?_ksTS=1683089742953_64&jsoncallback=jsonp65&action=showAction&n_s=new&event_submit_doGetSoon=true'
headers = {
'accept':' text/javascript, application/javascript, application/ecmascript, application/x-ecmascript, */*; q=0.01',
'accept-language':' zh-CN,zh;q=0.9,en;q=0.8',
'cookie':' ',
'referer':' https://dianying.taobao.com/?spm=a1z21.3046609.city.222.32c0112alijvBz&city=441800',
'user-agent':' Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/112.0.0.0 Safari/537.36',
'x-kl-ajax-request':' Ajax_Request',
'x-requested-with':' XMLHttpRequest',
}
request = urllib.request.Request(url=url, headers=headers)
response = urllib.request.urlopen(request)
content = response.read().decode('utf-8')
# 使用正则表达式提取 JSON 数据
match = re.search(r'\((.*)\)', content)
json_data = match.group(1)
# 将JSON数据写入文件
with open('D:\\taopiaopiao.json', 'w', encoding='utf-8') as fp:
json.dump(json.loads(json_data), fp, ensure_ascii=False)
# 从文件中加载 JSON 数据
with open('D:\\taopiaopiao.json', 'r', encoding='utf-8') as fp:
obj = json.load(fp)
# 打印演出名称和演出时间
for item in obj['returnValue']:
print(item['showName'], ":", item['openDay'])
评论 (0)